{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:02:12Z","timestamp":1789999332842,"version":"4.0.1"},"reference-count":38,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T00:00:00Z","timestamp":1771718400000},"content-version":"vor","delay-in-days":52,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Healthcare Tech Letters"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>This study investigated the efficacy of pre\u2010trained deep learning models for multi\u2010class classification of eye diseases, namely cataract, diabetic retinopathy, and glaucoma, using fundus images. Although CNN and transformer\u2010based models have been extensively explored separately in ophthalmic diagnostics, a direct comparative analysis remains limited. Moreover, recent high\u2010performing systems frequently rely on heavy backbones, ensembles, or large\u2010scale domain pretraining, which can be impractical for resource\u2010constrained screening pipelines. We evaluated three models, EfficientNetB3, MobileNetV2 and vision Transformer, with tailored modifications. An attention\u2010enhanced feature refinement module and the OpthaHead custom classifier enhanced EfficientNetB3 and MobileNetV2, while META customization optimized vision Transformer. The proposed design explicitly targets two practical bottlenecks observed in ophthalmic transfer learning, insufficient feature selectivity for subtle lesions and structural regions, and overfitting or instability in the final decision layers when training data are limited. The optimized EfficientNetB3 achieved a 10.84% improvement over its baseline with 96.04% accuracy, and MobileNetV2 improved by 11.26%, balancing accuracy and computational efficiency. META customization boosted vision Transformer performance by over 18%, showing that reducing model complexity benefits transformers on limited medical data. This study demonstrates strong performance for AI\u2010driven eye disease classification and highlights the potential of AI tools for early detection, improving clinical decision\u2010making and patient\u00a0outcomes.<\/jats:p>","DOI":"10.1049\/htl2.70067","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T04:46:01Z","timestamp":1771821961000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OpthaNet: Attention\u2010Integrated Architecture for High\u2010Precision Multi\u2010Class Ophthalmic Image Classification"],"prefix":"10.1049","volume":"13","author":[{"given":"Souhardo","family":"Rahman","sequence":"first","affiliation":[{"name":"Department of Computer Science American International University\u2010Bangladesh Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Nasif","family":"Safwan","sequence":"additional","affiliation":[{"name":"Department of Computer Science American International University\u2010Bangladesh Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1601-8793","authenticated-orcid":false,"given":"Mahamodul Hasan","family":"Mahadi","sequence":"additional","affiliation":[{"name":"Department of Computer Science American International University\u2010Bangladesh Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Iftekharul","family":"Mobin","sequence":"additional","affiliation":[{"name":"Department of Computer Science American International University\u2010Bangladesh Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-1631","authenticated-orcid":false,"given":"Muhammad Firoz","family":"Mridha","sequence":"additional","affiliation":[{"name":"Department of Computer Science American International University\u2010Bangladesh Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,2,22]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-03161-7"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-03101-5"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-02995-5"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2021.05.010"},{"issue":"1","key":"e_1_2_13_6_1","article-title":"Comparison of CNN Algorithms for Feature Extraction on Fundus Images to Detect Glaucoma","volume":"2022","author":"Sunanthini V.","year":"2022","journal-title":"Journal of Healthcare Engineering"},{"key":"e_1_2_13_7_1","doi-asserted-by":"crossref","unstructured":"P.Intaraprasit T. H.Bui andM. P.Paing \u201cMobilenetv2\u2010Based Deep Learning for Retinal Disease Classification on a Mobile Application \u201d in2023 15th Biomedical Engineering International Conference (BMEiCON)(IEEE 2023) 1\u20135.","DOI":"10.1109\/BMEiCON60347.2023.10322079"},{"issue":"1","key":"e_1_2_13_8_1","first-page":"1","article-title":"Classification of Eye Disease From Fundus Images Using EfficientNet","volume":"2","author":"Bulut B.","year":"2022","journal-title":"Artificial Intelligence Theory and Applications"},{"key":"e_1_2_13_9_1","doi-asserted-by":"crossref","unstructured":"B.PatroandAnshika \u201cMulti\u2010Label Classification of Retinal Diseases Using Hybrid Vision Transformer \u201d in2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)(IEEE 2024) 1\u20135.","DOI":"10.1109\/ICCCNT61001.2024.10725227"},{"key":"e_1_2_13_10_1","doi-asserted-by":"crossref","unstructured":"M.Sandler A.Howard M.Zhu A.Zhmoginov andL.\u2010C.Chen \u201cMobilenetv2: Inverted Residuals and Linear Bottlenecks \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2018) 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_13_11_1","unstructured":"M.TanandQ.Le \u201cEfficientnet: Rethinking Model Scaling for Convolutional Neural Networks \u201d inInternational Conference on Machine Learning(PMLR 2019) 6105\u20136114."},{"key":"e_1_2_13_12_1","unstructured":"A.Dosovitskiy \u201cAn Image is Worth 16\u00d7$\\times$16 Words: Transformers for Image Recognition at Scale \u201d preprint arXiv October 22 2020 https:\/\/doi.org\/10.48550\/arXiv.2010.11929."},{"key":"e_1_2_13_13_1","doi-asserted-by":"crossref","unstructured":"B.EmirandE.Colak \u201cPerformance Analysis of Pretrained Convolutional Neural Network Models for Ophthalmological Disease Classification \u201dArquivos Brasileiros de Oftalmologia87(2023): e2022\u20130124.","DOI":"10.5935\/0004-2749.2022-0124"},{"issue":"1","key":"e_1_2_13_14_1","first-page":"5971","article-title":"Eye Disease Detection Using Deep Learning Models With Transfer Learning Techniques","volume":"12","author":"Vardhan K. B.","year":"2025","journal-title":"EAI Endorsed Transactions on Scalable Information Systems"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2021.013390"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40998-022-00514-4"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.48084\/etasr.7294"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102059"},{"key":"e_1_2_13_19_1","doi-asserted-by":"crossref","unstructured":"S.Benbakreti S.Benbakreti andU.Ozkaya \u201cThe Classification of Eye Diseases From Fundus Images Based on CNN and Pretrained Models \u201d41 no.1(2024):155\u2013164.","DOI":"10.14311\/AP.2024.64.0001"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11152228"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.052153"},{"issue":"6","key":"e_1_2_13_22_1","first-page":"631","article-title":"Deep\u2010Ensemble Learning Models for the Detection and Classification of Eye Diseases Based on Engineering Feature Extraction With Efficientb6 and DensNet169","volume":"17","author":"Abdullah A. A.","year":"2024","journal-title":"International Journal of Intelligent Engineering & Systems"},{"key":"e_1_2_13_23_1","doi-asserted-by":"crossref","unstructured":"G.Rao SambasivaandS. D.Pande \u201cClassification of Fundus Diseases Using Hybrid Techniques Based on the Fused MobileNet and Handmade Traits \u201d inDoctoral Symposium on Computational Intelligence(Springer 2024) 615\u2013626.","DOI":"10.1007\/978-981-97-6318-4_47"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.2196\/27822"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119557"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.4103\/ijo.IJO_92_21"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2023.1197239"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1136\/bjo-2022-322183"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0299265"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15312"},{"key":"e_1_2_13_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33365-y"},{"key":"e_1_2_13_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-023-02810-5"},{"key":"e_1_2_13_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11090887"},{"key":"e_1_2_13_34_1","doi-asserted-by":"crossref","unstructured":"M. H.Mahadi S.Rahman M. N.Safwan andF.Ahmed \u201cVisionOcular: Transfer Learning With Self\u2010Attention for Multi\u2010Class Ocular Diagnosis \u201d in2025 International Conference on Quantum Photonics Artificial Intelligence and Networking (QPAIN)(IEEE 2025) 1\u20136.","DOI":"10.1109\/QPAIN66474.2025.11171736"},{"key":"e_1_2_13_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bea.2025.100196"},{"key":"e_1_2_13_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/app132011437"},{"key":"e_1_2_13_37_1","volume-title":"Indian Diabetic Retinopathy Image Dataset (IDRID)","author":"Porwal P.","year":"2018"},{"key":"e_1_2_13_38_1","unstructured":"A.BudaiandJ.Odstrcilik \u201cHigh Resolution Fundus (HRF) Image Database \u201dFriedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg published2013 https:\/\/www5.cs.fau.de\/research\/data\/fundus\u2010images\/."},{"key":"e_1_2_13_39_1","unstructured":"\u201cODIR\u20102019 Grand Challenge \u201d Grand Challenge accessed February 5 2026 https:\/\/odir2019.grand\u2010challenge.org\/."}],"container-title":["Healthcare Technology Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl2.70067","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/htl2.70067","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl2.70067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:15:24Z","timestamp":1789996524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/htl2.70067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/htl2.70067"],"URL":"https:\/\/doi.org\/10.1049\/htl2.70067","archive":["Portico"],"relation":{},"ISSN":["2053-3713","2053-3713"],"issn-type":[{"value":"2053-3713","type":"print"},{"value":"2053-3713","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-09-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70067"}}